Target detection based on improved swin transformer and cascade RCNN

Yu-chao Chen; Ming-ju Liang

doi:10.1117/12.3011400

8 November 2023 Target detection based on improved swin transformer and cascade RCNN

Yu-chao Chen, Ming-ju Liang

Proceedings Volume 12923, Third International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2023); 129231F (2023) https://doi.org/10.1117/12.3011400
Event: 3rd International Conference on Artificial Intelligence, Virtual Reality and Visualization (AIVRV 2023), 2023, Chongqing, China

Abstract

This paper proposes two improvements to address the issues of high complexity and computational burden in the Swin Transformer backbone network for feature extraction and the feature mismatch problem caused by coupled detection in the Cascade R-CNN detection network. First, a lightweight PoolFormer Block based on pooling is introduced in the third and fourth stages of the Swin-T network to reduce its complexity. Then, to improve the feature extraction capability of the lightweight Swin-T network, a coordinate attention mechanism is introduced. Second, the classification and regression tasks of objects in the Cascade R-CNN detection network are decoupled to alleviate the issue of feature mismatch in the two tasks and further improve detection performance. The experimental findings obtained from the PASCAL VOC dataset indicate that the proposed approach increased the average detection precision by 2.2% compared to the baseline model.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yu-chao Chen and Ming-ju Liang "Target detection based on improved swin transformer and cascade RCNN", Proc. SPIE 12923, Third International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2023), 129231F (8 November 2023); https://doi.org/10.1117/12.3011400

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available